EP 3996054 C0 20231227 - METHOD AND APPARATUS FOR IMAGE SEGMENTATION
Title (en)
METHOD AND APPARATUS FOR IMAGE SEGMENTATION
Title (de)
VERFAHREN UND VORRICHTUNG ZUR BILDSEGMENTIERUNG
Title (fr)
PROCÉDÉ ET APPAREIL DE SEGMENTATION D'IMAGE
Publication
Application
Priority
GR 20200100671 A 20201109
Abstract (en)
[origin: EP3996054A2] Broadly speaking, the present techniques generally relate to a method for training a machine learning, ML, model to perform semantic image segmentation, and to a computer-implemented method and apparatus for performing semantic image segmentation using a trained machine learning, ML, model. The training method enables a semantic image segmentation ML model that is able to make predictions faster, without significant loss in accuracy. The training method also enables the ML model to be implemented on apparatus with different hardware specifications, i.e. different computational power and memory, for example.
IPC 8 full level
G06V 10/26 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01); G06V 20/20 (2022.01); G06V 20/70 (2022.01)
CPC (source: EP US)
G06T 7/12 (2017.01 - US); G06V 10/26 (2022.01 - EP); G06V 10/70 (2022.01 - US); G06V 10/7792 (2022.01 - EP); G06V 10/82 (2022.01 - EP); G06V 10/95 (2022.01 - EP); G06V 20/20 (2022.01 - EP); G06V 20/70 (2022.01 - EP); G06T 2207/20081 (2013.01 - US)
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Participating member state (EPC – UP)
AT BE BG DE DK EE FI FR IT LT LU LV MT NL PT SE SI
DOCDB simple family (publication)
EP 3996054 A2 20220511; EP 3996054 A3 20220803; EP 3996054 B1 20231227; EP 3996054 C0 20231227; CN 116438570 A 20230714; EP 4300440 A2 20240103; EP 4300440 A3 20240320; US 2023128637 A1 20230427; WO 2022098203 A1 20220512
DOCDB simple family (application)
EP 21206453 A 20211104; CN 202180075275 A 20211109; EP 23210143 A 20211104; KR 2021016230 W 20211109; US 202217888138 A 20220815